Interpretability

Learning Robust Rationales for Model Explainability: A Guidance-Based Approach AAAI 2024 Learning the greatest common divisor: explaining transformer predictions ICLR 2024 Learning to Generate Rules for Realistic Few-Shot Relation Classification: An Encoder-Decoder Approach EMNLP 2024 Learning to Intervene on Concept Bottlenecks ICML 2024 Learning to Refine with Fine-Grained Natural Language Feedback EMNLP 2024 Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process IJCAI 2024 Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation ACL 2024 Learning to Understand: Identifying Interactions via the Möbius Transform NeurIPS 2024 Learning Transparent Reward Models via Unsupervised Feature Selection CoRL 2024 Learning Useful Representations of Recurrent Neural Network Weight Matrices ICML 2024 Learning Visual Abstract Reasoning through Dual-Stream Networks AAAI 2024 Learning Where to Edit Vision Transformers NeurIPS 2024 Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism EMNLP 2024 LeDex: Training LLMs to Better Self-Debug and Explain Code NeurIPS 2024 LegalDiscourse: Interpreting When Laws Apply and To Whom NAACL 2024 Legal Science and Compute Science: A Preliminary Discussions on How to Represent the “Penumbra” Cone with AI COLING 2024 Less is More: Fewer Interpretable Region via Submodular Subset Selection ICLR 2024 Let Models Speak Ciphers: Multiagent Debate through Embeddings ICLR 2024 Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification ACL 2024 Leveraging Graph Structures to Detect Hallucinations in Large Language Models ACL 2024 Leveraging Language Model Capabilities for Sound Event Detection Interspeech 2024 Leveraging Physical and Semantic Features of text item for Difficulty and Response Time Prediction of USMLE Questions NAACL 2024 LG-CAV: Train Any Concept Activation Vector with Language Guidance NeurIPS 2024 LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack AAAI 2024 Limitations of Human Identification of Automatically Generated Text COLING 2024